Abstract

Large Language Models (LLMs) have recently achieved significant progress in natural language processing tasks, including question answering and assisting users, such as in cloud computing. Cloud computing is a composite of various fields, including LLMs, which is a straightforward approach to enhancing the performance of the entire cloud. Therefore, AI-driven load balancing has been developed in cloud computing for a long period to benefit from machine learning to enhance the performance of cloud computing. This study presents a comparative evaluation of several state-of-the-art LLMs, including OpenAI GPT-4 and Google Gemini, with our proposed model (IaCloud1) in predicting the most appropriate load-balancing techniques in the cloud environment.

References

• Wayne Xin Zhao et al. A survey of large language models. Frontiers of Computer Science, 17(6):670651, 2023.
• N. Yang, M. Fan, W. Wang, and H. Zhang. Decision-making large language model for wireless communication: a comprehensive survey on key techniques. IEEE Communications Surveys & Tutorials, vol. 28, pp. 3055–3088, 2026. doi: 10.1109/COMST.2025.3614494.
• Peter Mell and Timothy Grance. The nist definition of cloud computing. NIST Special Publication 800-145, 2011.
• Y. Pei et al. Llm-based cost-aware task scheduling for cloud computing systems. Journal of Cloud Computing, 14:1–20, 2025.
• M. S. M. Pozi and Y. Sato. A data-augmented model routing framework for efficient LLM deployment in edge–cloud environments. The Journal of Supercomputing, vol. 81, Article 1573, 2025. doi: 10.1007/s11227-025-08034-8.
• Anouar Ben Halima and Hafssa Benaboud. Challenges of load balancing algorithms in cloud computing utilizing data mining tools. International Journal of Electrical and Computer Engineering (IJECE), 15(3):3449–3457, June 2025.
• R. M. Singh, L. K. Awasthi, and G. Sikka. Towards metaheuristic scheduling techniques in cloud and fog: an extensive taxonomic review. ACM Computing Surveys, vol. 55, no. 3, Article 50, pp. 1–43, 2022. doi: 10.1145/3494520.
• Anouar Ben Halima and Hafssa Benaboud. On combining clustering and classification algorithms to enhance load balancing in cloud computing. In Digital Technologies and Applications, volume 1640 of Lecture Notes in Networks and Systems, pages 3–13. Springer, 2026.
• X. Yu et al. Multi-objective routing for cloud-edge large language model services. arXiv preprint arXiv:2507.15553, 2025.
• J. Li, C. Xu, L. Jia, F. Wang, C. Zhang, and J. Liu. EACO-RAG: Towards distributed tiered LLM deployment using edge-assisted and collaborative RAG with adaptive knowledge update. arXiv preprint arXiv:2410.20299, 2024. doi: 10.48550/arXiv.2410.20299.
• A. Tekawade and S. Banerjee. A cost effective reliability aware scheduler for task graphs in multi-cloud system. arXiv preprint arXiv:2212.09166, 2022. doi: 10.48550/arXiv.2212.09166.
• N. Pasha, A. Agarwal, and R. Rastogi. Round robin approach for vm load balancing algorithm in cloud computing environment. International Journal of Advanced Research in Computer Science and Software Engineering, 4(5):34–39, 2014.
• R. Mishra. Ant colony optimization: a solution of load balancing in cloud. International Journal of Web & Semantic Technology, 3(2):33–50, 2012.
• S. Sethi. Efficient load balancing in cloud computing using fuzzy logic. IOSR Journal of Engineering, 2(7):65–71, 2012.
• M. S. Q. Z. Nine, M. A. K. Azad, S. Abdullah, and M. R. Rahman. Fuzzy logic based dynamic load balancing in virtualized data centers. In 2013 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), pp. 1–7, 2013. doi: 10.1109/FUZZ-IEEE.2013.6622384.
• G. Michael, K. L. Smith, and S. S. Vrbsky. Power-aware load balancing for cloud computing. In Lecture Notes in Engineering and Computer Science, volume 2193, pages 127–132, 2011.
• V. Nae, R. Prodan, and T. Fahringer. Cost-efficient hosting and load balancing of massively multiplayer online games. In Proceedings of the IEEE/ACM International Workshop on Grid Computing, pp. 9–16, 2010. doi: 10.1109/GRID.2010.5697956.
• Y. Lu, Q. Xie, G. Kliot, A. Geller, J. R. Larus, and A. Greenberg. Join-idle-queue: A novel load balancing algorithm for dynamically scalable web services. Performance Evaluation, 68(11):1056–1071, 2011.
• R. K. Mondal, E. Nandi, and D. Sarddar. Load balancing scheduling with shortest load first. International Journal of Grid and Distributed Computing, 8(4):171–178, 2015.
• D. A. Agarwal and S. Jain. Efficient optimal algorithm of task scheduling in cloud computing environment. International Journal of Computer Trends and Technology, 9(7):344–349, 2014.
• Z. C. Chaczko, V. Mahadevan, S. Aslanzadeh, and C. McDermid. Availability and load balancing in cloud computing. In International Conference on Computer and Software Modeling (ICCSM 2011), International Proceedings of Computer Science and Information Technology (IPCSIT), vol. 14, pp. 134–140, 2011.
• M. Randles, D. Lamb, and A. Taleb-Bendiab. Experiments with honeybee foraging inspired load balancing. In Proceedings of the International Conference on Developments in eSystems Engineering (DeSE 2009), pp. 240–247, 2009. doi: 10.1109/DeSE.2009.19.
• K. Dasgupta, B. Mandal, P. Dutta, J. K. Mandal, and S. Dam. A genetic algorithm (ga) based load balancing strategy for cloud computing. Procedia Technology, 10:340–347, 2013.
• B. Mondal, K. Dasgupta, and P. Dutta. Load balancing in cloud computing using stochastic hill climbing: a soft computing approach. Procedia Technology, 4:783–789, 2012.
• Y. Fang, F. Wang, and J. Ge. A task scheduling algorithm based on load balancing in cloud computing. In Lecture Notes in Computer Science, volume 6318, pages 271–277, 2010.
• N. J. Kansal and I. Chana. Cloud load balancing techniques: a step towards green computing. International Journal of Computer Science Issues, 9(1):238–246, 2012.
• S. Sidhu and M. Mittal. A new era to balance the load on cloud using vector dot load balancing method. International Journal of Technology and Computing, 2(4):413–418, 2016.
• V. K. Reddy, K. Deva Surya, M. Sai Praveen, B. Lokesh, A. Vishal, and K. Akhil. Performance analysis of load balancing algorithms in cloud computing environment. Indian Journal of Science and Technology, 9(18), 2016.
• N. Xuan Phi, C. T. Tin, L. N. Ky Thu, and T. C. Hung. Proposed load balancing algorithm to reduce response time and processing time on cloud computing. International Journal of Computer Networks & Communications, 10(3):87–98, 2018.
• H. Mehta, P. Kanungo, and M. Chandwani. Decentralized content aware load balancing algorithm for distributed computing environments. In Proceedings of the International Conference & Workshop on Emerging Trends in Technology (ICWET ’11), pp. 370–375, 2011. doi: 10.1145/1980022.1980102.
• A. Bhadani and S. Chaudhary. Performance evaluation of web servers using central load balancing policy over virtual machines on cloud. In COMPUTE 2010 - The 3rd Annual ACM Bangalore Conference, pages 1–4, 2010.
• X. Liu, L. Pan, C.-J. Wang, and J.-Y. Xie. A lock-free solution for load balancing in multi-core environment. In 2011 3rd International Workshop on Intelligent Systems and Applications (ISA), pp. 1–4, 2011. doi: 10.1109/ISA.2011.5873313.
• T. Kokilavani and D. I. George Amalarethinam. Load balanced minmin algorithm for static meta-task scheduling in grid computing. International Journal of Computer Applications, 20(2):42–48, 2011.